基于最小二乘支持向量机的时间序列模型及油气管线点腐蚀损伤行为的预测.docVIP

 基于最小二乘支持向量机的时间序列模型 及油气管线点腐蚀损伤行为的预测# 程光旭1，李珺1，范志超2* 5 10 15 20 25 30 35 40 （1. 西安交通大学能源与动力工程学院，西安 710049； 2. 合肥通用机械研究院科研管理部，合肥 230031） 摘要：点腐蚀常常存在于油气管线中，很容易造成管线穿孔或泄漏事故。因此，对其腐蚀深 度扩展行为进行预测具有非常重要的意义。本文利用最小二乘支持向量机（LS-SVM）建立了 油气管线内部点腐蚀深度时间序列预测模型。针对 LS-SVM 模型参数优化过程十分复杂的情 况，在标准粒子群优化（PSO）算法的基础上，引入均匀设计、新的自适应惯性权重和新的 速度更新公式这三种进化策略，提出了一种混合粒子群优化（HPSO）算法来改善全局寻优。 仿真实验显示：HPSO 算法具有更强的有哪些信誉好的足球投注网站能力和更高的收敛精度。工程实例应用结果表明： 与 GM(1,1)模型、自回归（AR）模型和 BP 神经网络（BP-NN）模型相比，LS-SVM 模型的预测 性能更好，为开展管线剩余寿命预测提供理论基础。 关键词：化工机械与设备；油气管线腐蚀；最小二乘支持向量机 中图分类号：TE832 The Time Series Analysis Model Based on Least Square Support Vector and Its Application in Prediction of Pitting Corrosion Behaviour for Oil-gas Pipeline Cheng Guangxu1, Li Jun1, Fan Zhichao2 (1. School of Energy and Power Engineering, Xian Jiaotong University,Xian 710049; 2. Department of Research Management,Hefei General Machinery Research Institute, HeFei 230031) Abstract: The pitting corrosion are usually existed in oil and gas pipelines, and the corrosion is easily to cause perforation or leak accident of the pipeline. Therefore, it is very significant to study the prediction of depth propagation behaviour. In this paper, based on the Least square support vector machine(LS-SVM), a time series analysis model is proposed to predict the pitting corrosion depth for oil and gas pipeline. As for the complex situation of parameter optimization process in LS-SVM model, a new Hybrid particle swarm optimization(HPSO) is presented by inducing of uniform design method, novel self-adaptive inertia weight and novel velocity updating strategy to improve the global optimization ability. The simulation experiment indicates that HPSO has more stronger search capability and more higher convergence precision. The results of a engineering case application show that LS-SVM model performs a better prediction performance compared with GM(1,1) model, auto-regrssion(AR) model and BP neural network model. Keywords: Chemical process machinery and equipment; pitting corrosion; le